Architecture Support for FPGA Multi-tenancy in the Cloud
Architecture Support for FPGA Multi-tenancy in the Cloud
复制标题
DOI：
10.1109/asap49362.2020.00030
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Joel Mandebi Mbongue;Alex Shuping;Pankaj Bhowmik;C. Bobda
中科院分区：
文献类型：
--
作者：
Joel Mandebi Mbongue;Alex Shuping;Pankaj Bhowmik;C. Bobda
云部署现在越来越多地将FPGA加速器作为虚拟实例的一部分。虽然FPGA本质上仍然是单租户的，但对硬件加速的需求不断增长将不可避免地导致对支持FPGA多租户的方法和架构的需求。在本文中，我们提出了一个架构，支持空间共享的FPGA设备之间的多个租户在云中。该架构实现了一个片上网络（NoC）设计的快速数据移动和低硬件占用。在Xilinx Virtex Ultrascale +上对所提出的架构进行原型设计，证明了片上数据移动的最大频率接近规格，虚拟实例访问硬件加速器的吞吐量也很高。与单租户部署相比，我们展示了类似的性能，同时提高了FPGA利用率（在我们的案例研究中，FPGA利用率提高了6倍），这是虚拟化的主要目标之一。总体而言，我们的NoC互连实现了比最先进的最大频率高出约2倍的最大频率和25.6 Gbps的带宽。
Cloud deployments now increasingly provision FPGA accelerators as part of virtual instances. While FPGAs are still essentially single-tenant, the growing demand for hardware acceleration will inevitably lead to the need for methods and architectures supporting FPGA multi-tenancy. In this paper, we propose an architecture supporting space-sharing of FPGA devices among multiple tenants in the cloud. The proposed architecture implements a network-on-chip (NoC) designed for fast data movement and low hardware footprint. Prototyping the proposed architecture on a Xilinx Virtex Ultrascale + demonstrated near specification maximum frequency for on-chip data movement and high throughput in virtual instance access to hardware accelerators. We demonstrate similar performance compared to single-tenant deployment while increasing FPGA utilization (we achieved $6 \times$ higher FPGA utilization with our case study), which is one of the major goals of virtualization. Overall, our NoC interconnect achieved about $2 \times$ higher maximum frequency than the state-of-the-art and a bandwidth of 25.6 Gbps.